Autoplay
Autocomplete
Previous Lesson
Complete and Continue
{ C Language } Deep Learning From Ground Up™
Getting Started
Introduction to Deep Learning (3:00)
Set Up
Setting up an Integrated Development Environment (IDE) (5:38)
Introduction to Neural Networks
The Single Input Single Output Neural Network (1:05)
Coding : Single Input Single Output Neural Network (10:24)
The Single Input Multiple Output Neural Network (2:30)
Coding : Single Input Multiple Output Neural Network (10:46)
The Multiple Input Single Output Neural Network (2:39)
Coding : Multiple Input Single Output Neural Network (13:11)
The Multiple Input Multiple Output Neural Network (2:49)
Coding : Multiple Input Multiple Output Neural Network (17:47)
The Hidden Layer Neural Network (2:37)
Coding : The Hidden Layer Neural Network (18:19)
Comparing and Finding Error (1:53)
Coding : Finding Error (9:24)
Understanding data representation in Machine Learning (1:18)
Understanding the "Learning" in Machine Learning (4:21)
Coding : Brute-force Learning (17:07)
Introduction to Gradient Descent (3:16)
Functional Description of a Biological Neuron (2:08)
Source Code Download
Introduction to Neural Network (Part 2)
Case Study : Building a Neural Network to Predict Muscle Gain (9:04)
Coding : Normalizing Datasets (14:42)
Coding : Random Initialization of Weights (16:06)
Understanding Activation Functions (3:41)
Coding : Forward Propagation (49:44)
Basics of Calculus (8:25)
Logistic Regression
Case Study : Building a Neural Network to Detect Cats (6:39)
Deep Neural Networks
Internals of a 2 layer Neural Network (3:01)
Understanding Computational Graphs (8:50)
Updating Parameters Effectively (3:33)
Understanding the Importance of Vectorization (9:05)
Summary of Back-propagation and Forward-propagation (0:40)
Initializing Parameters Effectively (0:38)
Understanding Layers and Units (1:12)
Understanding the Shapes (3:12)
Understanding Broadcasting in Programming (1:18)
Improving Neural Networks with Regularization Techniques
Overfitting and Underfitting (2:49)
Building a Complete Neural Network Library for Predicting Handwritten Numbers
Coding : Defining our Neural Network Structure (14:14)
Building Our Neural Network Library Utility Functions
Coding : Defining our Data Object Structure (9:38)
Coding : Implementing a Function to Read Data From a File (12:27)
Coding : Implementing a Function to Parse our Data (19:02)
Coding : Implementing more Utility Functions (8:44)
Building Our Neural Network Library Engine
Coding : Implementing the Forward Propagation Function (9:39)
Coding : Implementing the Back Propagation Function (13:08)
Coding : Implementing the NNPredict Function (3:23)
Coding : Implementing the NNBuild and NNTrain Functions (11:17)
Coding : Implementing the NNSaveModel and NNLoadModel Functions (10:10)
Coding : Implementing the NNPrint Function (7:11)
Testing our Neural Network Library
Coding : Training a Model to Predict Handwritten Digits (34:17)
Coding : Testing our Model (10:30)
Coding : Running Inference with our Model (9:08)
Closing
Closing Remarks
Teach online with
Overfitting and Underfitting
Lesson content locked
If you're already enrolled,
you'll need to login
.
Enroll in Course to Unlock